• Corpus ID: 237503417

Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data

  title={Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data},
  author={Hari Prasanna Das and Ryan Tran and Japjot Singh and Xiangyu Yue and Geoffrey H. Tison and Alberto L. Sangiovanni-Vincentelli and Costas J. Spanos},
$\textbf{Background:}$ At the onset of a pandemic, such as COVID-19, data with proper labeling/attributes corresponding to the new disease might be unavailable or sparse. Machine Learning (ML) models trained with the available data, which is limited in quantity and poor in diversity, will often be biased and inaccurate. At the same time, ML algorithms designed to fight pandemics must have good performance and be developed in a time-sensitive manner. To tackle the challenges of limited data, and… 

Figures and Tables from this paper

Expanding New Covid-19 Data with Conditional Generative Adversarial Networks
  • Haneen Majid, K. Ali
  • Computer Science
    Iraqi Journal for Electrical and Electronic Engineering
  • 2022
Conditional Generative Adversarial Networks (CGAN) is developed to produce synthetic images close to real images for the COVID-19 case and traditional augmentation that was used to expand the limited dataset then used to train by Customized deep detection model.
Conditional Synthetic Data Generation for Personal Thermal Comfort Models
It is proposed to implement a state-of-the-art conditional synthetic data generator to generate synthetic data corresponding to the low-frequency classes, and it is shown that the synthetic data generated has a distribution that mimics the real data distribution.
Likelihood Contribution based Multi-scale Architecture for Generative Flows
A novel multi-scale architecture that performs data dependent factorization to decide which dimensions should pass through more flow layers is proposed and a heuristic based on the contribution of each dimension to the total log-likelihood which encodes the importance of the dimensions is introduced.


CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training
A transfer learningbased framework utilizing normalizing flows, coupled with both maximum-likelihood and adversarial training, that can generate synthetic samples conditioned on them in the target domain by generating non-trivial augmentations via attribute and component transformations.
Synthetic Data Generation for Improved COVID-19 Epidemic Forecasting
This paper proposes a method of strengthening the forecasts from compartmental models by using short term pre-dictions from a curve fitting approach as synthetic data, and discusses the method of fitting this hybrid model in a generalized manner without reliance on region specific data, making this approach easy to adapt.
CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection
This research presents a method to generate synthetic chest X-ray (CXR) images by developing an Auxiliary Classifier Generative Adversarial Network (ACGAN) based model called CovidGAN and demonstrates that the synthetic images produced by this model can be utilized to enhance the performance of CNN for COVID-19 detection.
Reinforcement Learning for Optimization of COVID-19 Mitigation policies
This paper presents a novel agent-based pandemic simulator which, unlike traditional models, is able to model fine-grained interactions among people at specific locations in a community and an RL-based methodology for optimizing fine- grained mitigation policies within this simulator.
Meta-DermDiagnosis: Few-Shot Skin Disease Identification using Meta-Learning
This paper trains a neural network on few-shot image classification tasks based on an initial set of class labels / head classes of the distribution, prior to adapting the model for classification on a set of unseen / tail classes, and incorporates Group Equivariant convolutions (G-convolutions) for the Meta-DermDiagnosis network to improve disease identification performance.
COVIDNet-CT: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases From Chest CT Images
COVIDNet-CT, a deep convolutional neural network architecture that is tailored for detection of COVID-19 cases from chest CT images via a machine-driven design exploration approach, is introduced and the model and dataset are introduced.
Few-Shot Adversarial Domain Adaptation
This work provides a framework for addressing the problem of supervised domain adaptation with deep models by carefully designing a training scheme whereby the typical binary adversarial discriminator is augmented to distinguish between four different classes.
COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images
COVID-Net is introduced, a deep convolutional neural network design tailored for the detection of COVID-19 cases from chest X-ray (CXR) images that is open source and available to the general public, and COVIDx, an open access benchmark dataset comprising of 13,975 CXR images across 13,870 patient patient cases.
Breaking Medical Data Sharing Boundaries by Employing Artificial Radiographs
This work proposes to use generative models (GM) to produce high-resolution artificial radiographs, which are free of personal identifying information, and envision that this approach could lead to scalable databases of anonymous medical images enabling standardized radiomic analyses at multiple sites.
Visualizing Data using t-SNE
A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.